研究人员开发了一种新的对偶框架，用于约束在线凸优化，该框架无需 Slater 条件。这种自适应正则化方法稳定了对偶过程，为随机和对抗性约束提供了改进的遗憾界和约束违反界。该框架实现了强凸损失的对数遗憾，并为硬约束违反提供了保证。 AI
影响 这项研究推进了与机器学习算法相关的优化技术。
排序理由 该集群包含一篇详细介绍新优化框架的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.31480v1 Announce Type: new Abstract: We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints. For stochastic constraints, existing algorithms that achieve nearly optimal regret and constraint violation bounds ty…
We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints. For stochastic constraints, existing algorithms that achieve nearly optimal regret and constraint violation bounds typically rely on regularity assumptions such as S…